© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112838
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guarding
    -0.27
    oS
    -0.26
     ful
    -0.26
    åĩĢåĢ¼
    -0.25
    _Vector
    -0.25
     airing
    -0.24
    å®ģåİ¿
    -0.24
     testify
    -0.24
    ĭè¯ķ
    -0.24
     hast
    -0.23
    POSITIVE LOGITS
     context
    0.26
    .context
    0.26
    åī²
    0.25
    encoded
    0.25
    çļĦåħ³æ³¨
    0.25
    lä
    0.24
     angel
    0.24
     Strip
    0.24
    驱
    0.24
    shadow
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.